Alzheimer Disease Classification Using Improved VGG 19 Architecture

Alzheimer's disease (AD) is the most common form of dementia and may cause irreversible damage to memory cells. Numerous long-term effects emerge as Alzheimer's progresses. Because of this, it is essential to detect the condition as soon as possible. Accuracy of magnetic resonance imaging as a diagnostic tool for Alzheimer's disease is the primary subject of this investigation. The VGG-19 Convolutional Neural Network model is introduced in this research study. VGG-19 is a deep transfer learning model used to identify Alzheimer's disease in MRI images. It has been pre-trained on a big dataset. The three main phases of this research are preprocessing, feature extraction, and classification. The OASIS database provided the data utilised for this analysis. There are 373 MRI scans included in the analysis. This model uses just 20% of the data for actual testing, but uses the remaining 80% for training purposes. Current deep learning CNN models, including AlexNet, GoogLeNet, and VGG-16, are compared to and contrasted with the VGG-19 model. The examination of the model's performance makes use of the accuracy, recall, precision, specificity, and f-measure performance measures. Training and test data are compared and analysed separately for every validation.